AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing

Zhuo Wang, Zezheng Wang, Zitong Yu, Weihong Deng, Jiahong Li, Tingting Gao, Zhongyuan Wang

CVPR 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 213 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use SSAN-M instead of the strongest listed baselineFAS cross-dataset evaluation · M&I to C; M&I to OHTER(%): 31.06 -> 30.00; 30.73 -> 29.44Improved
Use SSAN-R instead of SSDG-RFAS cross-dataset evaluation · O&C&I to M; O&M&I to C; O&C&M to I; I&C&M to OHTER(%): 7.38 -> 6.67; 10.44 -> 10.00; 11.71 -> 8.88; 15.61 -> 13.72Improved
Use SSAN-R instead of ResNet18large-scale FAS benchmark · Protocol 1; Protocol 2_1; Protocol 2_2TPR@FPR 0.1%(%): 69.10$\pm$34.34 -> 78.45$\pm$31.98; 3.64$\pm$3.93 -> 6.58$\pm$5.56; 19.00$\pm$14.79 -> 31.61$\pm$23.33Improved
Add adversarial domain alignment to content features (ablation)SSAN-M · O&M&I to CHTER(%): 24.44 -> 16.67Improved
Add contrastive learning for shuffled style assemblies (ablation)SSAN-M · O&M&I to CHTER(%): 17.59 -> 16.67Improved
Add stop-gradient to self-assembly anchors (ablation)SSAN-M · O&M&I to CHTER(%): 20.93 -> 16.67Improved
Use relative soft supervision instead of hard supervision (ablation)SSAN-M · O&M&I to CHTER(%): 28.89 -> 16.67Improved
Use shuffled auxiliary assemblies for contrastive learning instead of SCL on self-assemblies (ablation)SSAN-M · O&M&I to CHTER(%): 23.70 -> 16.67Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy